Hasan Rıza Özçalık

Classification of EMG signals using wavelet neural network.

An accurate and computationally efficient means of classifying electromyographic (EMG) signal patterns has been the subject of considerable research effort in recent years. Quantitative analysis of EMG signals provides an important source of information for the diagnosis of neuromuscular disorders. Following the recent development of computer-aided EMG equipment, different methodologies in the time domain and frequency domain have been followed for quantitative analysis. In this study, feedforward error backpropagation artificial neural networks (FEBANN) and wavelet neural networks (WNN) based classifiers were developed and compared in relation to their accuracy in classification of EMG signals. In these methods, we used an autoregressive (AR) model of EMG signals as an input to classification system. A total of 1200 MUPs obtained from 7 normal subjects, 7 subjects suffering from myopathy and 13 subjects suffering from neurogenic disease were analyzed. The success rate for the WNN technique was 90.7% and for the FEBANN technique 88%. The comparisons between the developed classifiers were primarily based on a number of scalar performance measures pertaining to the classification. The WNN-based classifier outperformed the FEBANN counterpart. The proposed WNN classification may support expert decisions and add weight to EMG differential diagnosis.

RBF based induction motor control with a good nonlinearity compensation

This work introduces an artificial neural network based speed control system for AC induction motors. In motor control, Radial Basis Function (RBF) network and Volt-Hertz (V/f) method have been adopted as neural controller and scalar driving tool respectively. V/Hz method has been preferred for the sake of simplicity and well-known reliability. The proposed control scheme consists of two main parts; a RBF network and a reference model unit. RBF based main controller supplies appropriate control signals to the driving unit to compensate nonlinearity of the induction motor and track the reference model output. Reference model, is very stable linear filter which is supplying set values to be imitated by induction motor. The success of the proposed control scheme has been demonstrated by experimental results; induction motor has been able to track the prescribed speed trajectory with rather small errors and good stability under properly loading conditions.

A comparative analysis of FLC and ANFIS controller for vector controlled induction motor drive

This paper presents an adaptive neuro-fuzzy inference system (ANFIS) based speed control for indirect field oriented controlled induction motor drive. The obtaining of maximum torque and efficiency in the motor necessitates a successful nonlinear speed control method due to the non-linear structure of the system. In this work, a fuzzy logic controller (FLC) and ANFIS controller has been developed for speed control of induction motors. Parameters of ANFIS are tuned with on-line direct self-tuning method. The performance of proposed controllers has been examined in different working conditions. Simulation studies shows robustness and suitability of drive for high performance drive applications.

The analysis on the impact of the roof angle on electricity energy generation of photovoltaic panels in Kahramanmaras, Turkey—A case study for all seasons

Photovoltaic (PV) panels absorb solar energy most when solar radiation perpendicularly reaches on upon surface. This leads to the notion of optimal roof angle. Optical and geometrical properties of the panels are of vital importance in order to obtain maximum energy from the Sun. Therefore, this study focuses on the horizontal roof angle which has a crucial impact on the performance of PV panels. Total solar radiation, optimal roof angle and effects of different angles on PV panels in Kahramanmaras province of Turkey on different days are numerically and experimentally analyzed and discussed. Additionally, roof angle influences the amount of solar radiation reaching on the surface and varies depending on the geographic location and seasons. 7.9% more energy can be generated in the proposed systems where roof angle can be daily adjusted. This greatly influences the amount of solar energy when optimal roof angles are calculated annually depending on the seasons in a region. However, it is quite costly and c...

A Low Cost Shading Analyzer and Site Evaluator Design to Determine Solar Power System Installation Area

Shading analyzer systems are necessary for selecting the most suitable installation site to sustain enough solar power. Afterwards, changes in solar data throughout the year must be evaluated along with the identification of obstructions surrounding the installation site in order to analyze shading effects on productivity of the solar power system. In this study, the shading analysis tools are introduced briefly, and a new and different device is developed and explained to analyze shading effect of the environmental obstruction on the site on which the solar power system will be established. Thus, exposure duration of the PV panels to the sunlight can be measured effectively. The device is explained with an application on the installation area selected as a pilot site, Denizli, in Turkey.

Assessment and analysis on numerical and experimental performance of the photovoltaic systems for Germany and Turkey

Solar energy plants are popular due to their low cost, and environmental friendly and renewable nature. Germany is the leading country in the solar energy market in the world. Turkey also possesses a very high potential in terms of solar energy among European countries. The present study aims to draw attention to solar energy plants and define its applicability for these two countries. Two identical photovoltaic systems, installed in Turkey and Germany, were analyzed. First, we introduced the experimental results of two installed photovoltaic systems. Second, we numerically modelled two photovoltaic systems and processed the data with PVsyst in order to compare and verify experimental results. Numerical results display a good agreement with the experimental results, indicating that the performance of the modelling system is high, and that it can be used as a tentative photovoltaic system prior to installation. In addition, the solar energy capacities of Turkey and Germany are analyzed and discussed in detail.

Asenkron Motorların Online Adaptif Sinirsel-Bulanık Denetim (ANFIS) Sistemine Dayalı Hız Denetim Performansının İncelenmesi

Uc fazli asenkron motorlarin hiz denetiminde sistemin dogrusal olmayan yapisi, yuk momentindeki degisimler, parametre degisimleri ve bilinmeyen bozucu etkilerinden dolayi geleneksel PI tipi denetim ile iyi bir performans saglanamamaktadir. Bu nedenle asenkron motorun hiz denetiminde, daha iyi bir performans elde etmek icin adaptif kontrol yontemleri uygulanmaya baslamistir. Bu calismada vektor kontrollu asenkron motorun hiz denetiminde geleneksel PI denetim yerine modern denetim yontemlerinden olan adaptif sinirsel-bulanik denetim (ANFIS) sistemi onerilmistir. Bu calismanin esas amaci, PI denetimli calismadan elde edilen giris-cikis verileri kullanilarak onerilen denetleyici parametrelerini ayarlamak ve asenkron motorun hiz denetiminde yuksek performans elde etmektir. Her iki denetim sisteminin performansi MATLAB/Simulink ortaminda farkli calisma kosullarinda incelenmistir. Asenkron motorun hiz kontrolu simulasyon calismasinda, yukselme zamani, asim, yerlesme zamani ve surekli hal hatasi gibi performans parametreleri ayarlanarak onerilen denetim sistemi geleneksel PI denetime kiyasla daha iyi bir performans saglamistir. Ayrica, sistemde referans hizin degistirildigi ve yukun degistirildigi bolgelerde ANFIS, geleneksel PI tipi denetimden daha iyi bir performansa sahip oldugu simulasyon sonuclarindan gozlemlenmistir.

Üç Fazlı Asenkron Motor İçin Uzay Vektör Darbe Genişlik Modülasyonu Kullanan Yapay Sinir Ağı Temelli Adaptif Hız Kontrol Sistemi Tasarımı

Asenkron motorlarin gunumuz endustrisinde yaygin kullanimi bu motorlarin saglamligi, yuksek verimliligi ve isletme guvenilirliginden kaynaklanmaktadir. Bununla birlikte, oldukca karmasik ve dogrusal olmayan yapilarindan dolayi bu motorlarin kontrol edilmelerinde buyuk guclukler yasanmaktadir. Mikroislemci ve guc elektronigi alanlarindaki son gelismelerin yani sira yapay zekâ temelli yeni kontrol stratejileri asenkron motorlarinin daha etkin ve guvenilir sekilde kontrol edilmesini saglamistir. Guclu mikrodenetleyicilerden olan sayisal isaret islemciler ile motor kontrolunde kullanilan koordinat donusumleri, alan tahmin algoritmalari ve denetim algoritmalari gibi karmasik hesaplamalar yapilabilmektedir. Bilindigi gibi yapay zekâya dayali modern araclar arasinda yer alan yapay sinir aglari, dogrusal olmayan dinamik sistemlerin modellenmesi ve kontrolunde yaygin olarak kullanilmaktadir. Bu calismada uc fazli bir asenkron motorun hiz kontrol sistemi dsPIC30F6010A mikrodenetleyicisi kullanilarak gerceklestirilmistir. Rotor aki vektoru, vektor kontrolunun en verimli semasi olan dolayli alan yonlendirmeli kontrol teknigi kullanilarak tahmin edilir. Uc fazli eviricinin anahtarlamasinda uzay vektor darbe genislik modulasyon (UVDGM) teknigi kullanilmistir. Surucu sisteminin performansinin artirilmasi amaciyla radyal taban fonksiyonlu yapay sinir agi (RTYSA) temelli model referans adaptif kontrol (MRAK) metodu kullanilarak bir hiz denetimin algoritmasi gelistirilmistir. Asenkron motor farkli hiz ve yuk kosullari altinda calistirilarak onerilen kontrol algoritmasinin basarisi deneysel olarak test edilmistir. Deneysel sonuclar, onerilen kontrol yapisinin basarisini acikca gostermistir.

Designing a smart security camera system

Closed circuit TV systems have recently become an indispensable part of daily life. Cameras are of vital importance as significant elements of security systems in different buildings such as houses, stores and shopping malls. IP technology contributed to the development of security systems which witnessed rapid improvements in terms of smart image analysis. Recent security camera systems with smart video analysis serve a vital purpose. This study focuses on designing a smart security camera system.

Remote detection and assessment of solar energy potential analysis based on available roof surface area: case study in Kahramanmaras, Turkey

Abstract. Renewable energy has started to receive increasing attention due to various factors, such as scarcity of existing energy sources, high costs, global climate problems, etc. In this respect, solar energy has recently witnessed rapid developments due to its unlimited, carbon-free, environment-friendly, cost effective, and feasible nature. However, large pieces of land are necessary in order to install photovoltaic systems. Therefore, protection of arable lands and measurement of roof potentials are of vital importance in terms of reducing environment-friendly and renewable energy costs. Potential values of building roofs in Kahramanmaras province are calculated in detail thanks to various software and programs. Findings indicate that photovoltaic panels, which can generate a total amount of 430.348 MWp, can be installed on building roofs in Kahramanmaras province. Analysis of various parameters such as shading effect, safety factors, required usage area on the roofs, and tilt are also included in the calculations. This installed power may annually supply 693,977,463 kWh (≈694  GWh) for the region in question. In addition, CO2 emission may be reduced by 18,541.975 tons. This study sets an example for other regions and thus can also be performed for them.